Visual-Semantic Scene Understanding by Sharing Labels in a Context Network

Ishani Chakraborty, Ahmed Elgammal

Abstract:

We consider the problem of naming objects in complex, natural scenes containing widely varying object appearance
and subtly different names. Informed by cognitive research, we propose an approach based on sharing context
based object hypotheses between visual and lexical spaces. To this end, we present the Visual Semantic Integration
Model (VSIM) that represents object labels as entities shared between semantic and visual contexts and infers a new image by updating labels through context switching. At the core of VSIM is a semantic Pachinko Allocation Model and a visual nearest neighbor Latent Dirichlet Allocation Model. For inference, we derive an iterative Data Augmentation algorithm that pools the label probabilities and maximizes the joint label posterior of an image. Our model surpasses the performance of stateof-
art methods in several visual tasks on the challenging SUN09 dataset.